Fit cumulative distribution from kernel estimate.
Given a kernel density estimate, this function carries out a (very quick and dirty) numerical integration, and then fits a spline to get a function which can be used to look up cumulative probabilities.
smoothed.df(d)
d |
kernel density estimate |
The spline function approximating the df.
Ross Ihaka, ihaka@stat.auckland.ac.nz
x <- rnorm(1000) + ifelse(runif(1000) > .5, -3, 3) d <- density(x) F <- smoothed.df(d) # F returns cumulative probs # Plot the true (red) and estimated (blue) density functions par(mfrow=c(1,2)) curve(0.5 * dnorm(x, -3) + 0.5 * dnorm(x, 3), -7, 7, col="red") lines(d, col="blue") # Plot the true (red) and estimated (blue) distribution functions curve(0.5 * pnorm(x, -3) + 0.5 * pnorm(x, 3), -7, 7, col="red") curve(F(x), add=TRUE, col="blue")
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.